Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    scientific research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    			↵
    -0.07
     defin
    -0.06
    implementation
    -0.06
     oceans
    -0.06
     Modification
    -0.06
     systematically
    -0.06
    .get
    -0.06
    有些
    -0.06
    inne
    -0.06
    غر
    -0.06
    POSITIVE LOGITS
    REFER
    0.07
    ublice
    0.07
    orean
    0.07
    ومتر
    0.07
    .Dot
    0.06
     Grill
    0.06
    namese
    0.06
     saddened
    0.06
    _preds
    0.06
    ़त
    0.06
    Act Density 0.056%

    No Known Activations